What is MemoryLane for Claude Code?

MemoryLane is a specialized skill that gives Claude Code durable project memory by storing knowledge locally and injecting only relevant context into your AI interactions.

Can I manually edit or delete stored memories?

Yes, MemoryLane provides a comprehensive CLI for listing, updating, deleting, and curating memories to ensure your project's knowledge base remains accurate and high-quality.

How does MemoryLane save on token costs?

It uses context compression and selective injection, ensuring the AI only processes the most important information rather than re-reading entire files or large context blocks.

Is my project data stored securely?

Yes, MemoryLane extracts and stores all project knowledge locally within your project's .memorylane directory, keeping your data under your control.

What is the context rot guard feature?

The context rot guard ensures that injected memories never exceed a safe fraction of the model's context window, keeping the AI's performance optimal and avoiding information overload.

MemoryLane for Claude Code

Name: MemoryLane for Claude Code
Author: AWolf81

byAWolf81

生産性とワークフロー

Enables durable, compressed project memory for Claude Code to improve context relevance and reduce token costs.

概要

MemoryLane provides Claude Code with a persistent local memory system that extracts and stores crucial project knowledge. By identifying and injecting only the most relevant information back into the AI's context window, it prevents 'context rot' and significantly reduces token consumption. This skill ensures the AI agent retains a deep understanding of long-term project decisions, architectural patterns, and specific logic without overwhelming the model's prompt window with redundant data.

主な機能

Persistent local memory extraction and storage
Automatic context injection with context rot prevention
Detailed cost and token savings analytics
0 GitHub stars
Background sidecar server for seamless memory processing
Manual memory curation and management via CLI

ユースケース

Reducing LLM API costs by compressing project knowledge into high-density memories
Maintaining deep architectural context across long-running development projects
Recalling specific project decisions or legacy logic from past coding sessions

概要

主な機能

Persistent local memory extraction and storage
Automatic context injection with context rot prevention
Detailed cost and token savings analytics
0 GitHub stars
Background sidecar server for seamless memory processing
Manual memory curation and management via CLI

ユースケース

Reducing LLM API costs by compressing project knowledge into high-density memories
Maintaining deep architectural context across long-running development projects
Recalling specific project decisions or legacy logic from past coding sessions